Hypothesis Testing Examples and Analysis

0% found this document useful (0 votes)
278 views9 pages
This document provides examples of hypothesis testing problems with solutions. It includes: 1) Four examples of hypothesis tests with the null and alternative hypotheses stated, appropriate…

Uploaded by

Orvyn Ysmael
  • Problem 1 - Null and Alternative Hypotheses
  • Problem 2 - Standardized IQ Test
  • Problem 3 - Average Height Hypothesis
  • Problem 4 - Cookie Caloric Content
  • Problem 5 - Real Estate Price Hypothesis
  • Problem 6 - Student Age Report
  • Problem 7 - Home Ownership Survey
  • Problem 8 - Gender Proportion in Health Sector
  • Problem 9 - Murder Cases by Gender

CHECK YOUR PROGRESS

Name: Villariza, Lady Junette A. Score: ______


Time: TTH 5-8 PM
Instructor: Dr. Liza Lorena Jala

A. State the null and alternative hypothesis in words and in symbols for each conjecture.

1. A researcher thinks that if expectant mothers use vitamin pills, the birth weight of the babies will
increase. The average birth weight of the population is 8.6 pounds.
H0:  < 8.6 H1:  > 8.6

2. An engineer hypothesizes that the mean number of defects can be decreased in a manufacturing
process of compact disks by using robots instead of humans for certain tasks. The mean number of
defective disks per 1000 is 18.
H0:  > 18 H1:  < 18

m
er as
3. A psychologist feels that playing soft music during a test will change the results of the test. The

co
psychologist is not sure whether the grades will be higher or lower. In the past the mean scores was

eH w
73.

o.
H0:  = 73 H1:  = 73

rs e
ou urc
B. Directions: Use traditional methods for the following problems below.

1. A policeman in the National Police District claims that the number of car accidents along EDSA is 15
per week, on the average. To check his claim, car accidents were monitored for n = 36 randomly
o

selected weeks, resulting to a mean of x́ = 17 accidents and variance s 2 = 9. Does the sample
aC s

evidence contradict the policeman’s claim? Use α =0.05 to test to test the hypothesis. Source:
vi y re

PSA-SRTC Training Manual (2007)

Step 1
H0:  < 15
ed d

H1:  > 15
ar stu

Step 2
The significance level is .05
Step 3
We will use z test
is

Step 4
Th

Reject H0 if z>1.65 or p < 0.05


Step 5
x́−μ 0 17−15
¿ ¿
z s 3 = 4
sh

√n √ 36
Because the computed z of 4> critical z of 1.65, the null hypothesis is rejected. We can conclude that the sample
evidence does contradict the policeman’s claim.

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
2. A city Science High School uses a standardized IQ test to screen students for admission. It is known
that the population standard deviation of these IQ scores is 15. The school principal claimed that the
average IQ of the students in their school is 110. Miss Cruz, a researcher, wants to validate this claim.
She selected random sample of 50 students and administer the IQ test. She found that the mean IQ of
the sample is 105. Does this sample data provide sufficient evidence to reject the school principal’s
claim? Perform a test of hypothesis at 0.05 level of significance.

Step 1
H0:  > 110 H1:  < 110
Step 2
The significance level is .05
Step 3
We will use z test
Step 4
Reject H0 if z>1.65 or p < 0.05
Step 5

m
er as
105−110
¿
15

co
z = -2.357 = -2.36

eH w
√ 50
p(z<2.36) = 0.0091

o.
rs e
Because the computed z of 2.36> critical z of 1.65, the p of .0091< α of 0.05, the null hypothesis is rejected. She
ou urc
can conclude mean IQ of the sample is 105.

3. The average one-year-old (both sexes) is 29 inches tall. A random sample of 30 one-year-olds in a
o

large day care franchise resulted in the following heights. At α =0.05 , can it be concluded that
aC s

the average height differs from 29 inches?


vi y re

25 32 35 25 30
26.5 26 25.5 29.5 32
30 28.5 30 32 28
31.5 29 29.5 30 34
ed d

29 32 27 28 33
28 27 32 29 29.5
ar stu

Step 1
H0:  = 29 H1:  = 29
is

Step 2
The significance level is .05
Th

Step 3
We will use z test
Step 4
Reject H0 if z>1.96 or p < 0.05
sh

Step 5
29.45−29
¿
z 2.61 = 0.94
√ 30
p(z=0.94) = 0.353

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
Because the computed z of 0.94< critical z of 1.65, the p of .353> α of 0.05, the null hypothesis is not rejected. It
cannot be concluded that the average height differs from 29 inches.

4. A store manager hypothesizes that the average number of pages a person copies on the store’s copy
machine is less than 40. A sample of 50 customers’ orders is selected. At α =0.01 , is there enough
evidence to support the claim?
2 2 2 5 32
5 29 8 2 49
21 1 24 72 70
21 85 61 8 42
3 15 27 113 36
37 5 3 58 82
9 2 1 6 9
80 9 51 2 122
21 49 36 43 61
3 17 17 4 1

m
er as
Step 1

co
H0:  >40 H1:  <40

eH w
Step 2

o.
The significance level is .05
Step 3
rs e
ou urc
We will use z test
Step 4
Reject H0 if z<-2.33 or p < 0.05
Step 5
o

29.26−40
aC s

¿
z 30.63 = -3.17
vi y re

√50
p(z<-3.17) = 0.0008
ed d

Because the computed z of -3.17< critical z of -2.33, the p of .0008< α of 0.05, the null hypothesis is rejected.
ar stu

There is an enough evidence that the average number of pages a person copies on the store’s copy machine is
less than 40.

5. A manufacturer states that the average lifetime of its television sets is more than 84 months. The
is

standard deviation of the population is 10 months. One hundred sets are randomly selected and tested.
The average lifetime of the sample is 85.1 months. Test the claim that the average lifetime of the sets
Th

is more than 84 months, and find the p-value. Should the null hypothesis be rejected at α =0.01 ?

Step 1
H0: <84 H1: >84
sh

Step 2
The significance level is .01
Step 3
We will use z test
Step 4
Reject H0 if z>2.58 or p < 0.01

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
Step 5
x́− ¿ 85.1−84
z= ¿ √n = = 1.10
¿ 10/ √ 100
p(z>1.10) = 1-0.8643=0.1357

Because the computed z of 1.10< critical z of 2.58, the p of .1357> α of 0.01, the null hypothesis is not rejected.
There is no enough evidence the claim that the average lifetime of the sets is more than 84 months.

6. Suppose a statistician chose to test a hypothesis at α =0.01 . the critical value for a right-tailed
test is +2.33 . If the test value was 1.97 , what would the decision be? What would happen if,
after seeing the test value, she decided to choose α =0.05 ? What would the decision be? Explain
the contradiction, if there is one.

Step 1
Unknown
Step 2

m
er as
The significance level are .01 and 0.05
Step 3

co
Unknown

eH w
Step 4

o.
Reject H0 if z>2.33 or p < 0.01
rs e
Reject H0 if z>1.65 or p < 0.05
ou urc
Step 5
If the test value is 1.97 , then the null hypothesis is not rejected at 0.01 significance level. On the other
o

hand, if the test value is 1.97, then the null hypothesis is rejected at 0.05 significance level.
aC s

7. The SRTC gets its budget for a training program on the assumption that the average of the supplies is
vi y re

to be P12, 000 or less. To see if this claim is realistic, 10 supply figures are randomly obtained from
similar training programs. The sample has yielded a mean x́ =P12, 900 and s = P1, 100. Is the
mean greater than P12, 000? Use α =0.05 to test the hypothesis.
ed d

Step 1
ar stu

H0: <12,900 H1: >12,900


Step 2
The significance level is .01
is

Step 3
We will use t test
Th

Step 4
DF= 10-1=9
Reject H0 if t>1.833 or p < 0.05
Step 5
sh

12, 900−12000
t = = 2.59
1,100/ √10
p(t>2.59) = 0.0146

Because the computed t of 2.59> critical t of 1.83, the p of .0146< α of 0.05, the null hypothesis is rejected. There is
enough evidence that the mean greater than P12, 000.

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
8. The average 1-ounce chocolate chip cookie contains 110 calories. A random sample of 15 different
brands of 1-ounce chocolate chip cookies resulted in the following calorie amounts. At α =0.01
level, is there sufficient evidence that the average calorie content is greater than 110 calories?
100 125 150 160 185 125 155 110 145 160 100 150
140 135 120

Step 1
H0: <110 H1: >110
Step 2
The significance level is .01
Step 3
We will use t test
Step 4
DF= 15-1=14
Reject H0 if t>2.62 or p < 0.01

m
er as
Step 5
137.33−110

co
t = = 4.39

eH w
24.12/ √ 15

o.
Because the computed t of 4.39> critical t of 2.62, the null hypothesis is rejected. There is enough evidence that the
rs e
average calorie content is greater than 110 calories.
ou urc
9. The average running time for Broadway shows is 2 hours and 12 minutes. A producer in another city
claims that the length of time of productions in his city is the same. He samples 8 shows and finds the
o

time to be 2 hours and 5 minutes with a standard deviation of 11 minutes. Using α =0.05 , is the
aC s

producer correct?
vi y re

Step 1
H0: >132 H1: <132
Step 2
ed d

The significance level is .05


Step 3
ar stu

We will use t test


Step 4
DF= 8-1=7
is

Reject H0 if t>3 or p < 0.05


Step 5
Th

125−132
t = = -1.80 = 1.80
11/ √ 8
p(t<1.80) = 0.0574
sh

Because the computed t of 1.80 < critical t of 3, the null hypothesis is not rejected. There is not enough evidence that
the producer is correct.

10. From past experience, a teacher believes that the average score on a real estate exam is 75. A sample
of 20 students’ exam scores as follows:
80 68 72 73 76 81

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
71 71 65 50 63 71
70 70 76 75 69 70
72 74

Test the claim that the students’ average is still 75. Use α =0.01

Step 1
H0: =75 H1: =75
Step 2
The significance level is .01
Step 3
We will use t test
Step 4
DF= 20-1=19
Reject H0 if t>2.54 or p < 0.01
Step 5
70.85−75

m
t = = –2.83 = 2.83

er as
6.564 / √ 20

co
eH w
p(t=2.83) =0.0054

o.
Because the computed t of 2.83 > critical t of 2.54, the p of .0054< α of 0.01, the null hypothesis is rejected. There is
rs e
enough evidence that his claim is correct.
ou urc
11. A new laboratory technician reads a report that the average number of students using the computer
o

laboratory per hour was 16. To test this hypothesis, he selected a day at random and keeps track of the
aC s

number of students who used the lab over an 8-hour period. The results were as follows:
vi y re

20 24 18 16 16 19 21 23

At α =0.05 , test the claim that the average is actually 16.


ed d

Step 1
H0: =16 H1: =16
ar stu

Step 2
The significance level is .05
Step 3
is

We will use t test


Step 4
Th

DF= 8-1=7
Reject H0 if t>1.89 or p < 0.05
Step 5
19.625−16
sh

t = = 3.45
2.973/ √ 8

p(t=3.45) =0.0053

Because the computed t of 3.45 > critical t of 1.89, the p of .0053< α of 0.05, the null hypothesis is rejected. There is
enough evidence that his claim is correct.

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
12. A recent survey found that 64.7% of the population owns their homes. In a random sample of 150
heads of households, 92 responded that they owned their homes. At the 0.01 level of significance,
does that indicate a difference from the national proportion?

Step 1
H0: π < 0.647 H1: π > 0.647
Step 2
The significance level is .01.
Step 3
Use the z distribution for the test statistic
Step 4
Reject H0 if z<-2.58 or p < 0.01
Step 5
92
p−π −.647

m
150

er as
z= π (1−π ) = = -0.86 = 0.86
√ √ .647(1−.647)

co
n
150

eH w
p(z>-0.86) =1-0.8051=0.1949

o.
rs e
Because the computed z of -0.86 > critical z of 2.58, the p of .1949> α of 0.01, the null hypothesis is not rejected.
ou urc
There is no enough evidence that his claim is correct.

13. It has been reported that 40% of the adult population participate in computer hobbies during their
o

leisure time. A random sample of 180 adults found that 65 engaged in computer hobbies. At
α =0.01 , is there sufficient evidence to concluded that the proportion differs from 40%?
aC s
vi y re

Step 1
H0: π =.40 H1: π =.40
Step 2
ed d

The significance level is .01


Step 3
ar stu

We will use z test


Step 4
Reject H0 if z<-2.58 or p < 0.01
is

Step 5
65
p−π
Th

−.40
180
z= π (1−π ) = = -1.07
√ n
√ .4 o (1−.40)
180
sh

p(z=-1.07) =0.1423

Because the computed z of -1.07 > critical z of -2.58, the p of .1949> α of 0.01, the null hypothesis is not rejected.
There is no sufficient evidence to concluded that the proportion differs from 40%

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
14. The percentage of physicians who are women is 27.9%. In a survey of physicians employed by a
large university health system, 45 of 120 randomly selected physicians were women. Is there
sufficient evidence at 0.05 level of significance to conclude that the proportion of women physicians
at the university health system exceeds 27.9%.

Step 1
H0: π <.279 H1: π >.279
Step 2
The significance level is .05
Step 3
We will use z test
Step 4
Reject H0 if z>1.65 or p < 0.05
Step 5
45
p−π −.279
120
z= π (1−π ) = = 2.34

m
.279(1−.279)

er as
n
120

co
p(z>2.34) =1-0.9904 =0.0096

eH w
o.
Because the computed z of 2.34 > critical z of 1.65, the p of .0096< α of 0.05, the null hypothesis is rejected.

rs e
Therefore, we can conclude that the proportion of women physicians at the university health system exceeds
ou urc
27.9%.

15. A telephone company wants to advertise that more than 30% of all its customers have more than two
telephones. To support this ad, the company selects a sample of 200 customers and finds that 72 have
o

more than two telephones. Does the evidence support the ad? Use α =0.05 . Use p-value method.
aC s
vi y re

Step 1
H0: π <.30 H1: π >.30
Step 2
The significance level is .05
ed d

Step 3
ar stu

We will use z test


Step 4
Reject H0 if z>1.65 or p < 0.05
is

Step 5
72
p−π −.30
Th

200
z= π (1−π ) = = 1.85
√ n
√ .30(1−.30)
200
sh

p(z>1.85) =1-0.9678 =0.0322

Because the computed z of 1.85 > critical z of 1.65, the p of .032< α of 0.05, the null hypothesis is rejected.
Therefore, the evidence supports the ad.

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
16. Experts claim that 10% of murders are committed by women. Is there enough evidence to reject the
claim if in a sample of 67 murders, 10 were committed by women? At α =0.01 , test the
hypothesis using the p-value method.

Step 1
H0: π =.10 H1: π =.10
Step 2
The significance level is .01
Step 3
We will use z test
Step 4
Reject H0 if z>2.58 or p < 0.01
Step 5
10
p−π −.10
67
z= π (1−π ) = = 1.34
√ n
√ .1 o(1−.10)

m
67

er as
p(z=1.34) =0.9099

co
eH w
Because the computed z of 1.34 < critical z of 2.58, the p of .9099> α of 0.01, the null hypothesis is not rejected.

o.
There is no enough evidence to reject the that out of those murders, 10 were committed by women.
rs e
ou urc
o
aC s
vi y re
ed d
ar stu
is
Th
sh

This study source was downloaded by 100000819581655 from [Link] on 10-25-2021 19:44:19 GMT -05:00

[Link]
Powered by TCPDF ([Link])

Common questions

Powered by AI

The p-value measures the probability of obtaining a sample outcome at least as extreme as the one observed, assuming the null hypothesis is true. It is used to determine the statistical significance of the results. A smaller p-value indicates stronger evidence against the null hypothesis, guiding decisions such as rejecting or failing to reject it. For instance, in testing the average lifetime of TV sets, a p-value greater than α=0.01 led to not rejecting the null hypothesis . This interpretation informs whether the observed data provide enough evidence to support a different conclusion.

A researcher might choose a one-tailed test when they have a specific directional hypothesis to test, which provides greater power to detect an effect in one direction. This is appropriate when only an increase or a decrease is of interest, such as testing if vitamin intake raises birth weights . A two-tailed test is used when deviations in either direction are theoretically meaningful. Choosing a one-tailed test without justification could increase the risk of overlooking meaningful effects in the untested direction.

A z-test is typically used when the population variance is known and the sample size is large (n > 30), while a t-test is used when the population variance is unknown and the sample size is small (n < 30). The choice impacts the critical values used and the robustness of the test against deviations from normality. For example, in testing the claim that average calories in cookies is greater than 110, a t-test is suitable due to a small sample size . Using a z-test inappropriately could lead to incorrect conclusions about statistical significance.

Stating the null and alternative hypotheses explicitly is crucial because it defines the specific claims being tested and determines the direction of the test. This ensures clarity in what is being tested and avoids potential bias by establishing whether the test is one-tailed or two-tailed. In the study of birth weights with vitamin intake, clear formulation ensures correct analysis of whether vitamin intake has a significant effect . Incorrectly specifying these hypotheses can lead to erroneous conclusions about the population parameter of interest.

The sample size directly affects the power of a hypothesis test, which is the probability that the test correctly rejects a false null hypothesis. Larger sample sizes typically increase the power, reducing the chances of Type II errors by providing a more accurate estimate of the population parameter. For example, the hypothesis test regarding whether the average lifetime of television sets exceeds 84 months utilizes a sample size of 100, enhancing the reliability of the test conclusions .

The significance level, denoted as α, represents the probability of rejecting the null hypothesis when it is true. It sets the threshold for determining whether the observed data are extreme enough to reject the null hypothesis. Changing the significance level affects the decision margin: a lower α makes the test more stringent, reducing the risk of Type I errors but increasing the risk of Type II errors. For instance, a hypothesis test at α=0.01 is more stringent than at α=0.05, affecting decisions such as rejecting the null hypothesis of the average IQ being less than 110 based on a sample .

Checking assumptions like normality and equal variance is crucial because the validity of standard hypothesis testing procedures (e.g., t-tests and ANOVAs) depends on these assumptions. Violations can lead to inaccurate p-values, affecting Type I and II error rates. For instance, a t-test assuming normality might yield misleading results if the data are heavily skewed, such as testing for differences in calories among brands when sample sizes are small . Robust methods or data transformations should be considered when assumptions are violated.

In hypothesis testing, a Type I error occurs when we reject a true null hypothesis, whereas a Type II error happens when we fail to reject a false null hypothesis. For example, in testing if a manufacturing process reduces defects, a Type I error would mean concluding that robots reduce defects when they actually do not, while a Type II error would mean not detecting a reduction in defects when it actually exists . Selecting an appropriate significance level helps manage the rate of these errors.

Hypothesis testing provides a structured methodology to decide whether there is enough evidence to reject a null hypothesis about a population parameter based on sample data. By determining the likelihood that a sample result would occur under the null hypothesis, decision-makers can draw conclusions about the population. For example, in the case of determining if using robots in a manufacturing process decreases defects, the hypothesis testing framework allows an engineer to evaluate this conjecture statistically .

The standard deviation affects the variability within data, influencing the standard error of the mean, which in turn impacts the test statistic and the decision outcome. A smaller standard deviation typically leads to a more precise estimate and a larger test statistic, increasing the likelihood of rejecting the null hypothesis if an effect exists. In the case of testing average IQ at a school with a known population standard deviation, changing this value would potentially alter the z-score and conclusion .

CHECK YOUR PROGRESS
Name: Villariza, Lady Junette A.
Score: ______
Time: TTH 5-8 PM
Instructor: Dr. Liza Lorena Jala
A. Sta
2.
A city Science High School uses a standardized IQ test to screen students for admission. It is known
that the population s
Because the computed z of 0.94< cri
ti
cal
 z of 1.65, the p of .353> α of 0.05, the nul
l
 hypothesi
s i
s not rej
ected. It
Step 5
z = ´x−¿
¿√n
¿
 = 85.1−84
10/√100
 = 1.10
p(z>1.10) = 1-0.8643=0.1357
Because the computed z of 1.10< cri
ti
cal
 z of
8.
The average 1-ounce chocolate chip cookie contains 110 calories. A random sample of 15 different
brands of 1-ounce chocola
71 71
65
50
63
71
70 70
76
75
69
70
72 74
Test the claim that the students’ average is still 75. Use α=0.01
Step 1
H0: =75
H
12. A recent survey found that 64.7% of the population owns their homes. In a random sample of 150
heads of households, 92 re
14. The percentage of physicians who are women is 27.9%. In a survey of physicians employed by a
large university health syst
16. Experts claim that 10% of murders are committed by women. Is there enough evidence to reject the
claim if in a sample of

You might also like